Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Jiao, Binxing"'
Autor:
Peng, Wenjun, Yi, Jingwei, Wu, Fangzhao, Wu, Shangxi, Zhu, Bin, Lyu, Lingjuan, Jiao, Binxing, Xu, Tong, Sun, Guangzhong, Xie, Xing
Large language models (LLMs) have demonstrated powerful capabilities in both text understanding and generation. Companies have begun to offer Embedding as a Service (EaaS) based on these LLMs, which can benefit various natural language processing (NL
Externí odkaz:
http://arxiv.org/abs/2305.10036
Autor:
Yang, Nan, Ge, Tao, Wang, Liang, Jiao, Binxing, Jiang, Daxin, Yang, Linjun, Majumder, Rangan, Wei, Furu
We propose LLMA, an LLM accelerator to losslessly speed up Large Language Model (LLM) inference with references. LLMA is motivated by the observation that there are abundant identical text spans between the decoding result by an LLM and the reference
Externí odkaz:
http://arxiv.org/abs/2304.04487
To improve the performance of the dual-encoder retriever, one effective approach is knowledge distillation from the cross-encoder ranker. Existing works construct the candidate passages following the supervised learning setting where a query is paire
Externí odkaz:
http://arxiv.org/abs/2212.10192
Autor:
Wang, Liang, Yang, Nan, Huang, Xiaolong, Jiao, Binxing, Yang, Linjun, Jiang, Daxin, Majumder, Rangan, Wei, Furu
This paper presents E5, a family of state-of-the-art text embeddings that transfer well to a wide range of tasks. The model is trained in a contrastive manner with weak supervision signals from our curated large-scale text pair dataset (called CCPair
Externí odkaz:
http://arxiv.org/abs/2212.03533
Autor:
Zhu, Qiushi, Zhou, Long, Zhang, Ziqiang, Liu, Shujie, Jiao, Binxing, Zhang, Jie, Dai, Lirong, Jiang, Daxin, Li, Jinyu, Wei, Furu
Although speech is a simple and effective way for humans to communicate with the outside world, a more realistic speech interaction contains multimodal information, e.g., vision, text. How to design a unified framework to integrate different modal in
Externí odkaz:
http://arxiv.org/abs/2211.11275
Autor:
Yi, Jingwei, Wu, Fangzhao, Wu, Chuhan, Huang, Xiaolong, Jiao, Binxing, Sun, Guangzhong, Xie, Xing
Query-aware webpage snippet extraction is widely used in search engines to help users better understand the content of the returned webpages before clicking. Although important, it is very rarely studied. In this paper, we propose an effective query-
Externí odkaz:
http://arxiv.org/abs/2210.08809
Autor:
Shen, Tao, Geng, Xiubo, Tao, Chongyang, Xu, Can, Huang, Xiaolong, Jiao, Binxing, Yang, Linjun, Jiang, Daxin
In large-scale retrieval, the lexicon-weighting paradigm, learning weighted sparse representations in vocabulary space, has shown promising results with high quality and low latency. Despite it deeply exploiting the lexicon-representing capability of
Externí odkaz:
http://arxiv.org/abs/2208.14754
Retrieval models based on dense representations in semantic space have become an indispensable branch for first-stage retrieval. These retrievers benefit from surging advances in representation learning towards compressive global sequence-level embed
Externí odkaz:
http://arxiv.org/abs/2208.13661
Autor:
Wang, Liang, Yang, Nan, Huang, Xiaolong, Jiao, Binxing, Yang, Linjun, Jiang, Daxin, Majumder, Rangan, Wei, Furu
In this paper, we propose SimLM (Similarity matching with Language Model pre-training), a simple yet effective pre-training method for dense passage retrieval. It employs a simple bottleneck architecture that learns to compress the passage informatio
Externí odkaz:
http://arxiv.org/abs/2207.02578
Autor:
Zhou, Yucheng, Shen, Tao, Geng, Xiubo, Tao, Chongyang, Xu, Can, Long, Guodong, Jiao, Binxing, Jiang, Daxin
A ranker plays an indispensable role in the de facto 'retrieval & rerank' pipeline, but its training still lags behind -- learning from moderate negatives or/and serving as an auxiliary module for a retriever. In this work, we first identify two majo
Externí odkaz:
http://arxiv.org/abs/2206.08063